{
  "best_global_step": 55,
  "best_metric": 0.7241045236587524,
  "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-55",
  "epoch": 2.8947368421052633,
  "eval_steps": 1,
  "global_step": 55,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.7188231945037842,
      "learning_rate": 0.0,
      "loss": 3.2235,
      "step": 1
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 3.15524959564209,
      "eval_runtime": 3.3312,
      "eval_samples_per_second": 9.006,
      "eval_steps_per_second": 1.201,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.766629159450531,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.165,
      "step": 2
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 3.1018595695495605,
      "eval_runtime": 3.28,
      "eval_samples_per_second": 9.146,
      "eval_steps_per_second": 1.219,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.6206756234169006,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.8628,
      "step": 3
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 2.97302508354187,
      "eval_runtime": 3.2899,
      "eval_samples_per_second": 9.119,
      "eval_steps_per_second": 1.216,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.6644885540008545,
      "learning_rate": 0.0001,
      "loss": 2.9711,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 2.762944221496582,
      "eval_runtime": 3.2987,
      "eval_samples_per_second": 9.095,
      "eval_steps_per_second": 1.213,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.6135285496711731,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.7061,
      "step": 5
    },
    {
      "epoch": 0.2631578947368421,
      "eval_loss": 2.5087203979492188,
      "eval_runtime": 3.3091,
      "eval_samples_per_second": 9.066,
      "eval_steps_per_second": 1.209,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.5422775745391846,
      "learning_rate": 0.00016666666666666666,
      "loss": 2.4032,
      "step": 6
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 2.270092725753784,
      "eval_runtime": 3.3142,
      "eval_samples_per_second": 9.052,
      "eval_steps_per_second": 1.207,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.5579596161842346,
      "learning_rate": 0.0002,
      "loss": 2.272,
      "step": 7
    },
    {
      "epoch": 0.3684210526315789,
      "eval_loss": 2.0614399909973145,
      "eval_runtime": 3.3233,
      "eval_samples_per_second": 9.027,
      "eval_steps_per_second": 1.204,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.7365043759346008,
      "learning_rate": 0.00023333333333333333,
      "loss": 2.0297,
      "step": 8
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 1.8437634706497192,
      "eval_runtime": 3.3264,
      "eval_samples_per_second": 9.019,
      "eval_steps_per_second": 1.202,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.7677823901176453,
      "learning_rate": 0.0002666666666666667,
      "loss": 1.8911,
      "step": 9
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 1.615093469619751,
      "eval_runtime": 3.3357,
      "eval_samples_per_second": 8.994,
      "eval_steps_per_second": 1.199,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.7033586502075195,
      "learning_rate": 0.0003,
      "loss": 1.654,
      "step": 10
    },
    {
      "epoch": 0.5263157894736842,
      "eval_loss": 1.4461504220962524,
      "eval_runtime": 3.3549,
      "eval_samples_per_second": 8.942,
      "eval_steps_per_second": 1.192,
      "step": 10
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.721517026424408,
      "learning_rate": 0.0003333333333333333,
      "loss": 1.5364,
      "step": 11
    },
    {
      "epoch": 0.5789473684210527,
      "eval_loss": 1.3645799160003662,
      "eval_runtime": 3.361,
      "eval_samples_per_second": 8.926,
      "eval_steps_per_second": 1.19,
      "step": 11
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.7304323315620422,
      "learning_rate": 0.00036666666666666667,
      "loss": 1.3689,
      "step": 12
    },
    {
      "epoch": 0.631578947368421,
      "eval_loss": 1.272360920906067,
      "eval_runtime": 3.3759,
      "eval_samples_per_second": 8.887,
      "eval_steps_per_second": 1.185,
      "step": 12
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.6370911002159119,
      "learning_rate": 0.0004,
      "loss": 1.329,
      "step": 13
    },
    {
      "epoch": 0.6842105263157895,
      "eval_loss": 1.19339120388031,
      "eval_runtime": 3.3835,
      "eval_samples_per_second": 8.867,
      "eval_steps_per_second": 1.182,
      "step": 13
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5493318438529968,
      "learning_rate": 0.00043333333333333337,
      "loss": 1.1991,
      "step": 14
    },
    {
      "epoch": 0.7368421052631579,
      "eval_loss": 1.154818058013916,
      "eval_runtime": 3.3971,
      "eval_samples_per_second": 8.831,
      "eval_steps_per_second": 1.177,
      "step": 14
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.4599643051624298,
      "learning_rate": 0.00046666666666666666,
      "loss": 1.2358,
      "step": 15
    },
    {
      "epoch": 0.7894736842105263,
      "eval_loss": 1.1299824714660645,
      "eval_runtime": 3.4098,
      "eval_samples_per_second": 8.798,
      "eval_steps_per_second": 1.173,
      "step": 15
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.5700777173042297,
      "learning_rate": 0.0005,
      "loss": 1.206,
      "step": 16
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": 1.1079914569854736,
      "eval_runtime": 3.4063,
      "eval_samples_per_second": 8.807,
      "eval_steps_per_second": 1.174,
      "step": 16
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.44451233744621277,
      "learning_rate": 0.0004993910125649561,
      "loss": 1.2374,
      "step": 17
    },
    {
      "epoch": 0.8947368421052632,
      "eval_loss": 1.076997995376587,
      "eval_runtime": 3.4099,
      "eval_samples_per_second": 8.798,
      "eval_steps_per_second": 1.173,
      "step": 17
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.382600337266922,
      "learning_rate": 0.0004975670171853926,
      "loss": 1.0959,
      "step": 18
    },
    {
      "epoch": 0.9473684210526315,
      "eval_loss": 1.0459389686584473,
      "eval_runtime": 3.4174,
      "eval_samples_per_second": 8.779,
      "eval_steps_per_second": 1.17,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3735465109348297,
      "learning_rate": 0.0004945369001834514,
      "loss": 1.1433,
      "step": 19
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0354558229446411,
      "eval_runtime": 3.41,
      "eval_samples_per_second": 8.798,
      "eval_steps_per_second": 1.173,
      "step": 19
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.36878153681755066,
      "learning_rate": 0.0004903154239845797,
      "loss": 1.0467,
      "step": 20
    },
    {
      "epoch": 1.0526315789473684,
      "eval_loss": 1.0118752717971802,
      "eval_runtime": 3.4023,
      "eval_samples_per_second": 8.818,
      "eval_steps_per_second": 1.176,
      "step": 20
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 0.3709339499473572,
      "learning_rate": 0.0004849231551964771,
      "loss": 1.0453,
      "step": 21
    },
    {
      "epoch": 1.1052631578947367,
      "eval_loss": 0.9837953448295593,
      "eval_runtime": 3.3826,
      "eval_samples_per_second": 8.869,
      "eval_steps_per_second": 1.183,
      "step": 21
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 0.32317909598350525,
      "learning_rate": 0.0004783863644106502,
      "loss": 1.0573,
      "step": 22
    },
    {
      "epoch": 1.1578947368421053,
      "eval_loss": 0.9650039076805115,
      "eval_runtime": 3.3888,
      "eval_samples_per_second": 8.853,
      "eval_steps_per_second": 1.18,
      "step": 22
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 0.3465510606765747,
      "learning_rate": 0.00047073689821473173,
      "loss": 0.9613,
      "step": 23
    },
    {
      "epoch": 1.2105263157894737,
      "eval_loss": 0.9524248838424683,
      "eval_runtime": 3.389,
      "eval_samples_per_second": 8.852,
      "eval_steps_per_second": 1.18,
      "step": 23
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.341265469789505,
      "learning_rate": 0.00046201202403910646,
      "loss": 1.0765,
      "step": 24
    },
    {
      "epoch": 1.263157894736842,
      "eval_loss": 0.9478815197944641,
      "eval_runtime": 3.3934,
      "eval_samples_per_second": 8.841,
      "eval_steps_per_second": 1.179,
      "step": 24
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.32804617285728455,
      "learning_rate": 0.0004522542485937369,
      "loss": 0.9063,
      "step": 25
    },
    {
      "epoch": 1.3157894736842106,
      "eval_loss": 0.9379161596298218,
      "eval_runtime": 3.394,
      "eval_samples_per_second": 8.839,
      "eval_steps_per_second": 1.179,
      "step": 25
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 0.31782791018486023,
      "learning_rate": 0.0004415111107797445,
      "loss": 0.9969,
      "step": 26
    },
    {
      "epoch": 1.368421052631579,
      "eval_loss": 0.9347817897796631,
      "eval_runtime": 3.3909,
      "eval_samples_per_second": 8.847,
      "eval_steps_per_second": 1.18,
      "step": 26
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.3140616714954376,
      "learning_rate": 0.0004298349500846628,
      "loss": 0.9423,
      "step": 27
    },
    {
      "epoch": 1.4210526315789473,
      "eval_loss": 0.9298030138015747,
      "eval_runtime": 3.4047,
      "eval_samples_per_second": 8.811,
      "eval_steps_per_second": 1.175,
      "step": 27
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.3035232126712799,
      "learning_rate": 0.0004172826515897146,
      "loss": 0.8544,
      "step": 28
    },
    {
      "epoch": 1.4736842105263157,
      "eval_loss": 0.920465350151062,
      "eval_runtime": 3.4152,
      "eval_samples_per_second": 8.784,
      "eval_steps_per_second": 1.171,
      "step": 28
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 0.36378970742225647,
      "learning_rate": 0.00040391536883141455,
      "loss": 1.0175,
      "step": 29
    },
    {
      "epoch": 1.526315789473684,
      "eval_loss": 0.9069837331771851,
      "eval_runtime": 3.4214,
      "eval_samples_per_second": 8.768,
      "eval_steps_per_second": 1.169,
      "step": 29
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.3729051947593689,
      "learning_rate": 0.0003897982258676867,
      "loss": 0.9851,
      "step": 30
    },
    {
      "epoch": 1.5789473684210527,
      "eval_loss": 0.8988735675811768,
      "eval_runtime": 3.4109,
      "eval_samples_per_second": 8.795,
      "eval_steps_per_second": 1.173,
      "step": 30
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 0.3581544756889343,
      "learning_rate": 0.000375,
      "loss": 0.9229,
      "step": 31
    },
    {
      "epoch": 1.631578947368421,
      "eval_loss": 0.8822915554046631,
      "eval_runtime": 3.3783,
      "eval_samples_per_second": 8.88,
      "eval_steps_per_second": 1.184,
      "step": 31
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.28150516748428345,
      "learning_rate": 0.00035959278669726934,
      "loss": 0.94,
      "step": 32
    },
    {
      "epoch": 1.6842105263157894,
      "eval_loss": 0.8713746666908264,
      "eval_runtime": 3.4041,
      "eval_samples_per_second": 8.813,
      "eval_steps_per_second": 1.175,
      "step": 32
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 0.30831000208854675,
      "learning_rate": 0.00034365164835397803,
      "loss": 1.0407,
      "step": 33
    },
    {
      "epoch": 1.736842105263158,
      "eval_loss": 0.8603693842887878,
      "eval_runtime": 3.417,
      "eval_samples_per_second": 8.78,
      "eval_steps_per_second": 1.171,
      "step": 33
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 0.31896907091140747,
      "learning_rate": 0.00032725424859373687,
      "loss": 0.9185,
      "step": 34
    },
    {
      "epoch": 1.7894736842105263,
      "eval_loss": 0.849823534488678,
      "eval_runtime": 3.4154,
      "eval_samples_per_second": 8.784,
      "eval_steps_per_second": 1.171,
      "step": 34
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.29725414514541626,
      "learning_rate": 0.0003104804738999169,
      "loss": 0.978,
      "step": 35
    },
    {
      "epoch": 1.8421052631578947,
      "eval_loss": 0.8390634655952454,
      "eval_runtime": 3.4119,
      "eval_samples_per_second": 8.793,
      "eval_steps_per_second": 1.172,
      "step": 35
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.3137111961841583,
      "learning_rate": 0.00029341204441673266,
      "loss": 0.9221,
      "step": 36
    },
    {
      "epoch": 1.8947368421052633,
      "eval_loss": 0.8293085098266602,
      "eval_runtime": 3.3951,
      "eval_samples_per_second": 8.836,
      "eval_steps_per_second": 1.178,
      "step": 36
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 0.267716646194458,
      "learning_rate": 0.0002761321158169134,
      "loss": 1.0078,
      "step": 37
    },
    {
      "epoch": 1.9473684210526314,
      "eval_loss": 0.8227899670600891,
      "eval_runtime": 3.3926,
      "eval_samples_per_second": 8.843,
      "eval_steps_per_second": 1.179,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3097141683101654,
      "learning_rate": 0.0002587248741756253,
      "loss": 1.0386,
      "step": 38
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8196889758110046,
      "eval_runtime": 3.3913,
      "eval_samples_per_second": 8.846,
      "eval_steps_per_second": 1.179,
      "step": 38
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 0.29532116651535034,
      "learning_rate": 0.00024127512582437484,
      "loss": 0.9046,
      "step": 39
    },
    {
      "epoch": 2.0526315789473686,
      "eval_loss": 0.8109915852546692,
      "eval_runtime": 3.3856,
      "eval_samples_per_second": 8.861,
      "eval_steps_per_second": 1.181,
      "step": 39
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.3160407245159149,
      "learning_rate": 0.00022386788418308668,
      "loss": 0.8684,
      "step": 40
    },
    {
      "epoch": 2.1052631578947367,
      "eval_loss": 0.799045979976654,
      "eval_runtime": 3.3859,
      "eval_samples_per_second": 8.86,
      "eval_steps_per_second": 1.181,
      "step": 40
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 0.2594124674797058,
      "learning_rate": 0.00020658795558326743,
      "loss": 0.8051,
      "step": 41
    },
    {
      "epoch": 2.1578947368421053,
      "eval_loss": 0.7873298525810242,
      "eval_runtime": 3.3873,
      "eval_samples_per_second": 8.857,
      "eval_steps_per_second": 1.181,
      "step": 41
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 0.2573184370994568,
      "learning_rate": 0.0001895195261000831,
      "loss": 0.7542,
      "step": 42
    },
    {
      "epoch": 2.2105263157894735,
      "eval_loss": 0.7783879637718201,
      "eval_runtime": 3.3897,
      "eval_samples_per_second": 8.85,
      "eval_steps_per_second": 1.18,
      "step": 42
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 0.3050247132778168,
      "learning_rate": 0.00017274575140626317,
      "loss": 0.8833,
      "step": 43
    },
    {
      "epoch": 2.263157894736842,
      "eval_loss": 0.7714616060256958,
      "eval_runtime": 3.4031,
      "eval_samples_per_second": 8.815,
      "eval_steps_per_second": 1.175,
      "step": 43
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.27206432819366455,
      "learning_rate": 0.00015634835164602198,
      "loss": 0.8176,
      "step": 44
    },
    {
      "epoch": 2.3157894736842106,
      "eval_loss": 0.7637041807174683,
      "eval_runtime": 3.4006,
      "eval_samples_per_second": 8.822,
      "eval_steps_per_second": 1.176,
      "step": 44
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.24384012818336487,
      "learning_rate": 0.00014040721330273062,
      "loss": 0.7616,
      "step": 45
    },
    {
      "epoch": 2.3684210526315788,
      "eval_loss": 0.7560217380523682,
      "eval_runtime": 3.4005,
      "eval_samples_per_second": 8.822,
      "eval_steps_per_second": 1.176,
      "step": 45
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 0.25645551085472107,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.7888,
      "step": 46
    },
    {
      "epoch": 2.4210526315789473,
      "eval_loss": 0.7505295872688293,
      "eval_runtime": 3.3925,
      "eval_samples_per_second": 8.843,
      "eval_steps_per_second": 1.179,
      "step": 46
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 0.27820125222206116,
      "learning_rate": 0.00011020177413231333,
      "loss": 0.7584,
      "step": 47
    },
    {
      "epoch": 2.473684210526316,
      "eval_loss": 0.7445800304412842,
      "eval_runtime": 3.3928,
      "eval_samples_per_second": 8.842,
      "eval_steps_per_second": 1.179,
      "step": 47
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.23925091326236725,
      "learning_rate": 9.608463116858542e-05,
      "loss": 0.7504,
      "step": 48
    },
    {
      "epoch": 2.526315789473684,
      "eval_loss": 0.7403488755226135,
      "eval_runtime": 3.4026,
      "eval_samples_per_second": 8.817,
      "eval_steps_per_second": 1.176,
      "step": 48
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 0.32143712043762207,
      "learning_rate": 8.271734841028553e-05,
      "loss": 0.8269,
      "step": 49
    },
    {
      "epoch": 2.5789473684210527,
      "eval_loss": 0.7371814250946045,
      "eval_runtime": 3.3997,
      "eval_samples_per_second": 8.824,
      "eval_steps_per_second": 1.177,
      "step": 49
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.2628876864910126,
      "learning_rate": 7.016504991533726e-05,
      "loss": 0.7076,
      "step": 50
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 0.7335822582244873,
      "eval_runtime": 3.4029,
      "eval_samples_per_second": 8.816,
      "eval_steps_per_second": 1.175,
      "step": 50
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 0.30318617820739746,
      "learning_rate": 5.848888922025553e-05,
      "loss": 0.7792,
      "step": 51
    },
    {
      "epoch": 2.6842105263157894,
      "eval_loss": 0.7297669053077698,
      "eval_runtime": 3.3726,
      "eval_samples_per_second": 8.895,
      "eval_steps_per_second": 1.186,
      "step": 51
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.3162338435649872,
      "learning_rate": 4.7745751406263163e-05,
      "loss": 0.7217,
      "step": 52
    },
    {
      "epoch": 2.736842105263158,
      "eval_loss": 0.728228747844696,
      "eval_runtime": 3.3989,
      "eval_samples_per_second": 8.827,
      "eval_steps_per_second": 1.177,
      "step": 52
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 0.2733875513076782,
      "learning_rate": 3.798797596089351e-05,
      "loss": 0.8098,
      "step": 53
    },
    {
      "epoch": 2.7894736842105265,
      "eval_loss": 0.7270908355712891,
      "eval_runtime": 3.4122,
      "eval_samples_per_second": 8.792,
      "eval_steps_per_second": 1.172,
      "step": 53
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.26100900769233704,
      "learning_rate": 2.9263101785268254e-05,
      "loss": 0.7631,
      "step": 54
    },
    {
      "epoch": 2.8421052631578947,
      "eval_loss": 0.7254647016525269,
      "eval_runtime": 3.4244,
      "eval_samples_per_second": 8.761,
      "eval_steps_per_second": 1.168,
      "step": 54
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.2827248275279999,
      "learning_rate": 2.1613635589349755e-05,
      "loss": 0.7716,
      "step": 55
    },
    {
      "epoch": 2.8947368421052633,
      "eval_loss": 0.7241045236587524,
      "eval_runtime": 3.4133,
      "eval_samples_per_second": 8.789,
      "eval_steps_per_second": 1.172,
      "step": 55
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2315465393725440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}